Development of Pneumatic Quadrupedal Robot Performing Multiple Gaits by Simple Motor Commands
Yugo Kajiwara, Shuhei Ikemoto, Koh Hosoda
- Year
- 2018
- Citations
- 3
Abstract
A new approach of controlling quadrupedal robots would be posed by the recent breakthroughs in machine learning. Considering that these techniques typically require many trials to figure out adequate control inputs, the design specialized for this purpose will benefit. In this study, we are trying to develop a new quadrupedal robot driven by pneumatic cylinders centrally mounted on the body for archiving the simplicity of the mechanical design and the ability of performing multiple gaits. In this paper, we demonstrate the design of the developed pneumatic quadrupedal robot and indicate the robot can perform multiple gaits.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002